# Datawizz AI

## Docs

- [Client Access](https://docs.datawizz.ai/access-control/client-access.md): Enable user-level authentication and authorization with JWT tokens
- [Rate Limits](https://docs.datawizz.ai/access-control/rate-limits.md): Control API usage with fine-grained rate limits for keys and users
- [Virtual Keys](https://docs.datawizz.ai/access-control/virtual-keys.md): Manage access to AI models and track usage across applications
- [Training Apple Foundation Model Adapters](https://docs.datawizz.ai/afm/apple-foundation-model-adapters.md): Train, evaluate and deploy custom adapter for the Apple Foundation Model for on-device inference.
- [Edit Log](https://docs.datawizz.ai/api-reference/endpoint/patch_log.md): Edit an existing log in the system
- [Submit Feedback Signal](https://docs.datawizz.ai/api-reference/endpoint/post_feedback.md): Submit a feedback signal to assess model performance for a specific inference. Feedback signals are used for reinforcement learning and model improvement.
- [Introduction](https://docs.datawizz.ai/api-reference/introduction.md): Additional API documentation for the Datawizz Platform
- [Continuous Learning](https://docs.datawizz.ai/continuous-learning.md): Use Datawizz to continuously improve your models with new data
- [Attachment Processing [Beta]](https://docs.datawizz.ai/endpoints/attachment-processing.md): Send a wide variety of files to be processed by our AI models, including videos, office documents and PDFs.
- [Routing](https://docs.datawizz.ai/endpoints/routing.md): Learn how to route requests to different models based on custom logic
- [Structured Outputs](https://docs.datawizz.ai/endpoints/structured-outputs.md): Generate consistent JSON responses with JSON Schema
- [Automated Evaluations](https://docs.datawizz.ai/evaluation/automated-evaluations.md): Evaluate AI models automatically using Datawizz
- [Custom Evaluators](https://docs.datawizz.ai/evaluation/custom-evaluators.md): Create and use custom evaluators in Datawizz
- [Manual Evaluation](https://docs.datawizz.ai/evaluation/manual.md): Learn how to compare multiple models side-by-side and evaluate their performance
- [Using Datawizz with Langfuse](https://docs.datawizz.ai/integrations/langfuse.md): Use Datawizz with Langfuse
- [Using Datawizz with LangSmith](https://docs.datawizz.ai/integrations/langsmith.md): Export LangSmith traces and import them into Datawizz
- [Introduction](https://docs.datawizz.ai/introduction.md): Welcome to the home of your new documentation
- [Anonymizing Logs (PII Removal)](https://docs.datawizz.ai/logs/anonymizing-logs.md): Remove PII from logs to ensure user privacy & compliance
- [Feedback Signals](https://docs.datawizz.ai/logs/feedback.md): Collect structured feedback signals to improve AI model performance
- [Vercel AI SDK](https://docs.datawizz.ai/logs/libraries/vercel-ai-sdk.md): Using Datawizz with Vercel AI SDK
- [Metadata and Tagging](https://docs.datawizz.ai/logs/metadata-and-tagging.md): Add and manage metadata and tags for logs
- [Recording Requests](https://docs.datawizz.ai/logs/recording-requests.md): Learn how to record and manage your LLM requests with the Datawizz platform
- [Supported LLMs](https://docs.datawizz.ai/logs/supported-llms.md): Comprehensive list of LLM providers and models supported by Datawizz
- [Datasets](https://docs.datawizz.ai/models/datasets.md): Create, import, and manage datasets for training and evaluation
- [Model Deployment](https://docs.datawizz.ai/models/model-deployment.md): Deploy your models to various providers.
- [Model Training](https://docs.datawizz.ai/models/training-models.md): Train your first specialize language model with Datawizz.
- [Training parameters](https://docs.datawizz.ai/models/training-parameters.md)
- [Reranker Models](https://docs.datawizz.ai/models/training-reranker.md): API request/response for reranker inference and data format for reranker training
- [Platform Overview](https://docs.datawizz.ai/platform-overview.md): A brief overview of the Datawizz platform
- [Build Custom Plugins](https://docs.datawizz.ai/plugins/build-custom-plugins.md): Extend and customize request/response processing with custom logic
- [Plugins](https://docs.datawizz.ai/plugins/plugins.md): Extend and customize request/response processing with custom logic
- [Block Substrings](https://docs.datawizz.ai/public-plugins/block-substrings.md): Blocks or redacts requests containing specific substrings. Useful for filtering unwanted content or enforcing content policies.
- [Document Input Processing](https://docs.datawizz.ai/public-plugins/document-input-processing.md): Convert PDFs, Word, PowerPoint, and Excel documents into clean markdown for LLM processing. Uses Microsoft's MarkItDown with optional LLM-powered image descriptions.
- [Public Plugins](https://docs.datawizz.ai/public-plugins/index.md): Pre-built plugins for common use cases
- [Invisible Text](https://docs.datawizz.ai/public-plugins/invisible-text.md): Detects and removes non-printable, invisible Unicode characters to maintain text integrity and prevent steganography-based attacks.
- [Llama Guard 3](https://docs.datawizz.ai/public-plugins/llama-guard-3.md): Uses Meta's Llama Guard 3 model for content safety classification. Can detect and block unsafe content across 14 hazard categories including violence, hate speech, self-harm, and more.
- [Presidio Image PII Redaction](https://docs.datawizz.ai/public-plugins/presidio-image-pii-redaction.md): Extracts text from images via OCR, detects PII within the text, and returns redacted images with sensitive information obscured to protect privacy in multimodal AI requests.
- [Presidio PII Detection](https://docs.datawizz.ai/public-plugins/presidio-pii-detection.md): Analyzes AI requests for personally identifiable information (PII) using Microsoft Presidio and blocks requests containing sensitive data like emails, phone numbers, SSNs, and credit cards.
- [Presidio PII Redaction](https://docs.datawizz.ai/public-plugins/presidio-pii-redaction.md): Automatically detects and redacts PII from text in AI requests using configurable methods including replacement, masking, hashing, or encryption before the request reaches the AI model.
- [Regex Detect](https://docs.datawizz.ai/public-plugins/regex-detect.md): Scans messages for regex patterns and rejects or redacts matches. Useful for filtering sensitive information like emails, phone numbers, or credit card numbers.
- [Video Input Processing](https://docs.datawizz.ai/public-plugins/video-input-processing.md): Transform videos into LLM-compatible content by extracting frames, audio, and transcripts. Supports YouTube, TikTok, direct URLs, and works with any vision-enabled LLM.
- [Quickstart](https://docs.datawizz.ai/quickstart.md): Start routing your LLM requests through Datawizz to collect and organize your data.
- [Get Started with Self Hosting](https://docs.datawizz.ai/self-host/get-started.md): Deploy Datawizz on your own infrastructure using Docker Compose
- [Scaling Out ClickHouse](https://docs.datawizz.ai/self-host/scaling-clickhouse.md): Run ClickHouse on a separate instance for data redundancy and performance
- [Scaling Out the Router & Logger](https://docs.datawizz.ai/self-host/scaling-gateway.md): Run the AI Gateway, Request Logger, and Evaluator Runner on separate instances for horizontal scaling
- [Scaling Out Inference Workers](https://docs.datawizz.ai/self-host/scaling-inference.md): Deploy inference workers on separate instances for horizontal scaling

## OpenAPI Specs

- [openapi](https://docs.datawizz.ai/api-reference/openapi.json)